Training in progress, step 2420, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c13d002cd5898fbea8c6256b9a1e54172018693f368e3379c2c894ca5e77fc10
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35eb29dd25af9a8a4ac8376e1e30d381fe888dc09546aa3ab9da0345f784512a
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15e917e193825f3e9c2ccb5caa408e418df427cd28a39f56540cb7dda3e90bb7
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 18.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -4346,6 +4346,24 @@
|
|
| 4346 |
"mean_token_accuracy": 0.6466387540102005,
|
| 4347 |
"num_tokens": 8786506.0,
|
| 4348 |
"step": 2410
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4349 |
}
|
| 4350 |
],
|
| 4351 |
"logging_steps": 5,
|
|
@@ -4365,7 +4383,7 @@
|
|
| 4365 |
"attributes": {}
|
| 4366 |
}
|
| 4367 |
},
|
| 4368 |
-
"total_flos": 4.
|
| 4369 |
"train_batch_size": 4,
|
| 4370 |
"trial_name": null,
|
| 4371 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 18.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2420,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4346 |
"mean_token_accuracy": 0.6466387540102005,
|
| 4347 |
"num_tokens": 8786506.0,
|
| 4348 |
"step": 2410
|
| 4349 |
+
},
|
| 4350 |
+
{
|
| 4351 |
+
"epoch": 18.576923076923077,
|
| 4352 |
+
"grad_norm": 0.0,
|
| 4353 |
+
"learning_rate": 3.7930000000000004e-05,
|
| 4354 |
+
"loss": 1.7275,
|
| 4355 |
+
"mean_token_accuracy": 0.6533702045679093,
|
| 4356 |
+
"num_tokens": 8804613.0,
|
| 4357 |
+
"step": 2415
|
| 4358 |
+
},
|
| 4359 |
+
{
|
| 4360 |
+
"epoch": 18.615384615384617,
|
| 4361 |
+
"grad_norm": 0.0,
|
| 4362 |
+
"learning_rate": 3.7905000000000004e-05,
|
| 4363 |
+
"loss": 1.6716,
|
| 4364 |
+
"mean_token_accuracy": 0.6637963593006134,
|
| 4365 |
+
"num_tokens": 8823585.0,
|
| 4366 |
+
"step": 2420
|
| 4367 |
}
|
| 4368 |
],
|
| 4369 |
"logging_steps": 5,
|
|
|
|
| 4383 |
"attributes": {}
|
| 4384 |
}
|
| 4385 |
},
|
| 4386 |
+
"total_flos": 4.471487507084083e+17,
|
| 4387 |
"train_batch_size": 4,
|
| 4388 |
"trial_name": null,
|
| 4389 |
"trial_params": null
|